{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T10:16:22Z","timestamp":1789035382256,"version":"build-2803163510"},"reference-count":28,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T00:00:00Z","timestamp":1788998400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001409","name":"Science and Engineering Research Board (SERB), Department of Science and Technology (DST), Government of India","doi-asserted-by":"publisher","award":["EEQ\/2023\/000053"],"award-info":[{"award-number":["EEQ\/2023\/000053"]}],"id":[{"id":"10.13039\/501100001409","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Tomography"],"abstract":"<jats:p>Background: Accurate breast lesion classification and localization from mammograms remain challenging because lesions vary in size, morphology, density, contrast, and boundary clarity. This study proposes MSF-Swin-ICFNet, an image-derived Multi-Scale Swin Transformer framework with Image-Derived Cross-Scale Fusion (ICF) for joint benign\u2013malignant classification and lightweight lesion localization. Methods: The proposed framework extracts hierarchical representations from four Swin Transformer stages and aligns, adaptively recalibrates, and fuses these multi-scale features into a shared representation for classification and lesion-mask prediction. The model was evaluated on CBIS-DDSM, comprising 891 patients and 1592 mammograms, and RTM, comprising 573 patients and 10,070 mammograms. Patient-level stratified partitioning was used to ensure that mammograms and associated annotations from the same patient remained within a single data partition. Classification was evaluated using accuracy, precision, recall, F1-score, and AUC-ROC, while lesion localization was assessed using the Dice coefficient. Results: MSF-Swin-ICFNet achieved strong mammogram-level classification performance on the patient-disjoint test cohorts. On CBIS-DDSM, the model achieved 0.949 accuracy, 0.931 F1-score, and 0.985 AUC-ROC. On RTM, it achieved 0.968 accuracy, 0.956 F1-score, and 0.992 AUC-ROC. The corresponding Dice coefficients for lesion localization were 0.786 on CBIS-DDSM and 0.878 on RTM. Ablation experiments further supported the contribution of cross-scale fusion, scale recalibration, feature refinement, and the boundary-aware localization head. Conclusions: MSF-Swin-ICFNet demonstrates promising retrospective performance for image-based breast lesion classification with complementary lesion localization. The results support the technical potential of adaptive hierarchical feature fusion for mammographic analysis. However, the model is not intended as a standalone diagnostic system, and independent multicentre validation and radiologist reader studies are required before clinical deployment.<\/jats:p>","DOI":"10.3390\/tomography12090130","type":"journal-article","created":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:13:03Z","timestamp":1789031583000},"page":"130","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MSF-Swin-ICFNet: An Image-Derived Multi-Scale Swin Transformer Framework with Cross-Scale Feature Fusion for Breast Lesion Classification and Segmentation in Mammograms"],"prefix":"10.3390","volume":"12","author":[{"given":"Narayanam R. S.","family":"Lakshmi Prasanthi","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Vignan\u2019s Foundation for Science, Technology & Research (Deemed to be University), Vadlamudi, Guntur 522 213, AP, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8957-8532","authenticated-orcid":false,"given":"N. Thirupathi","family":"Rao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Vignan\u2019s Institute of Information Technology(A), Visakhapatnam 530 049, AP, India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2824-8134","authenticated-orcid":false,"given":"S. Deva","family":"Kumar","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Vignan\u2019s Foundation for Science, Technology & Research (Deemed to be University), Vadlamudi, Guntur 522 213, AP, India"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"170177","DOI":"10.1038\/sdata.2017.177","article-title":"A curated mammography data set for use in computer-aided detection and diagnosis research","volume":"4","author":"Lee","year":"2017","journal-title":"Sci. Data"},{"key":"ref_2","unstructured":"Sawyer-Lee, R., Gimenez, F., Hoogi, A., and Rubin, D. (2026, May 26). Curated Breast Imaging Subset of Digital Database for Screening Mammography (CBIS-DDSM) [Data Set]. The Cancer Imaging Archive. Available online: https:\/\/www.cancerimagingarchive.net\/collection\/cbis-ddsm\/."},{"key":"ref_3","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","volume":"Volume 9351","author":"Ronneberger","year":"2015","journal-title":"Proceedings of the Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Zhou, Z., Siddiquee, M.M.R., Tajbakhsh, N., and Liang, J. (2018). UNet++: A nested U-Net architecture for medical image segmentation. Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer.","DOI":"10.1007\/978-3-030-00889-5_1"},{"key":"ref_5","unstructured":"Oktay, O., Schlemper, J., Le Folgoc, L., Lee, M., Heinrich, M., Misawa, K., Mori, K., McDonagh, S., Hammerla, N.Y., and Kainz, B. (2018). Attention U-Net: Learning where to look for the pancreas. arXiv."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021). Swin Transformer: Hierarchical vision Transformer using shifted windows. Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref_7","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., and Gelly, S. (2021, January 3\u20137). An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale. Proceedings of the International Conference on Learning Representations, Virtual."},{"key":"ref_8","unstructured":"Chen, J., Lu, Y., Yu, Q., Luo, X., Adeli, E., Wang, Y., Lu, L., Yuille, A.L., and Zhou, Y. (2021). TransUNet: Transformers make strong encoders for medical image segmentation. arXiv."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Cao, H., Wang, Y., Chen, J., Jiang, D., Zhang, X., Tian, Q., and Wang, M. (2022). Swin-Unet: Unet-like pure Transformer for medical image segmentation. Proceedings of the European Conference on Computer Vision Workshops, Springer.","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"AQurri, L., and Erol, B. (2023). Improved U-Net with attention for medical image segmentation. Sensors, 23.","DOI":"10.3390\/s23208589"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"106626","DOI":"10.1016\/j.compbiomed.2023.106626","article-title":"DCSAU-Net: A deeper and more compact split-attention U-Net for medical image segmentation","volume":"154","author":"Xu","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"27318","DOI":"10.1038\/s41598-024-78648-0","article-title":"An open codebase for enhancing transparency in deep learning-based breast cancer diagnosis utilizing CBIS-DDSM data","volume":"14","author":"Liao","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"102618","DOI":"10.1016\/j.media.2022.102618","article-title":"Beyond fine-tuning: Classifying high resolution mammograms using function-preserving transformations","volume":"82","author":"Wei","year":"2022","journal-title":"Med. Image Anal."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"12041","DOI":"10.1038\/s41598-025-96101-8","article-title":"Multi-scale conv-attention U-Net for medical image segmentation","volume":"15","author":"Pan","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"37103","DOI":"10.1038\/s41598-025-21146-8","article-title":"A multi stage deep learning model for accurate segmentation and classification of breast lesions in mammography","volume":"15","author":"Ahmad","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Wang, H., Wei, L., Liu, B., Li, J., Li, J., Fang, J., and Mooney, C. (2025). Transformer-Based Explainable Model for Breast Cancer Lesion Segmentation. Appl. Sci., 15.","DOI":"10.3390\/app15031295"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"103320","DOI":"10.1016\/j.media.2024.103320","article-title":"Mammography classification with multi-view deep learning techniques: Investigating graph and transformer-based architectures","volume":"99","author":"Manigrasso","year":"2025","journal-title":"Med. Image Anal."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Takahashi, K., Zeng, Y., Zhang, Z., Ichiji, K., Usuzaki, T., Inamori, R., Liu, H., and Homma, N. (2025). Transformer-based Deep Learning Models with Shape Guidance for Predicting Breast Cancer in Mammography Images. J. Imaging Inform. Med.","DOI":"10.1007\/s10278-025-01773-3"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"8941","DOI":"10.1038\/s41598-026-37969-y","article-title":"A deep learning framework for breast cancer diagnosis using Swin Transformer and Dual-Attention Multi-scale Fusion Network","volume":"16","author":"Aldawsari","year":"2026","journal-title":"Sci. Rep."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Lee, W., Lee, H., Lee, H., Park, E.K., Nam, H., and Kooi, T. (2023). Transformer-based Deep Neural Network for Breast Cancer Classification on Digital Breast Tomosynthesis Images. Radiol. Artif. Intell., 5.","DOI":"10.1148\/ryai.220159"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Sarker, S., Sarker, P., Bebis, G., and Tavakkoli, A. (2024). MV-Swin-T: Mammogram Classification with Multi-view Swin Transformer. arXiv.","DOI":"10.1109\/ISBI56570.2024.10635578"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Rautela, K., Kumar, D., and Kumar, V. (2025). Modified Transformer-Based Pixel Segmentation for Breast Tumor Detection. Int. J. Imaging Syst. Technol., 35.","DOI":"10.1002\/ima.70166"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Narayanam, L.P.R.S., Rao, T.N., and Kumar, D.S. (2025). SwinCAMF-Net: Explainable Cross-Attention Multimodal Swin Network for Mammogram Analysis. Diagnostics, 15.","DOI":"10.3390\/diagnostics15233037"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Devnath, L., Janzen, I., Ho, C., Melosky, B., Lam, S., MacAulay, C., and Yuan, R. (2026). Fusion of Clinical and Deep Learning Features for Predicting Pembrolizumab Monotherapy Response in Advanced Non-Small Cell Lung Cancer. J. Clin. Med., 15.","DOI":"10.3390\/jcm15124536"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"109432","DOI":"10.1016\/j.compbiomed.2024.109432","article-title":"Enhanced breast mass segmentation in mammograms using a hybrid transformer UNet model","volume":"184","author":"Mohammadi","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"38893","DOI":"10.1038\/s41598-025-22649-0","article-title":"A multi-scale attention-based Swin transformer model for medical images segmentation","volume":"15","author":"Houshmand","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Ankoji, G., Rao, N.T., Ramana, C.V.V., Bhattacharyya, D., and Kim, T.-H. (2026). LAM-CATNet: Lambda-aware multi-scale cross-attention Swin transformer network for mammogram classification. Sci. Rep.","DOI":"10.1038\/s41598-026-51401-5"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1007\/s42452-026-08434-2","article-title":"Smart medical support system and Swin transformer framework for breast cancer detection and segmentation in mammograms","volume":"8","author":"Abugabah","year":"2026","journal-title":"Discov. Appl. Sci."}],"container-title":["Tomography"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2379-139X\/12\/9\/130\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T09:57:58Z","timestamp":1789034278000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2379-139X\/12\/9\/130"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,10]]},"references-count":28,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9]]}},"alternative-id":["tomography12090130"],"URL":"https:\/\/doi.org\/10.3390\/tomography12090130","relation":{},"ISSN":["2379-139X"],"issn-type":[{"value":"2379-139X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,10]]}}}